COVID-19 Analysis
Katie Forthman
Wed May 27 09:15:19 2020
Click here for interactive plots:
Click here to see how cities and counties overlap:
Compare COVID stats to Neighborhood Factors
data.cor <- cor(county.Demo_and_Covid.allcounties[,-1], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
Compare COVID stats to 500 cities data and Neighborhood Factors
data.cor2 <- cor(county.Demo_and_Covid.500counties[,-c(1:2)], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor2, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
corrplot.mixed(data.cor2[7:13,c(1:5, 14:42,6)], upper = 'ellipse', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
—-Linear Mixed Effects Model —-
this.lme <- lmer("total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)", data = county.Demo_and_Covid.500counties)## Warning: Some predictor variables are on very different scales: consider
## rescaling
## Warning: Some predictor variables are on very different scales: consider
## rescalingprint(summary(this.lme), correlation=TRUE)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## "total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)"
## Data: county.Demo_and_Covid.500counties
##
## REML criterion at convergence: -1275.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.2790 -0.3614 -0.0339 0.2674 5.8004
##
## Random effects:
## Groups Name Variance Std.Dev.
## stateID (Intercept) 0.000006065 0.002463
## Residual 0.000015258 0.003906
## Number of obs: 192, groups: stateID, 35
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) -0.0109765532 0.0115715114 97.6903819289
## Affluence 0.0048095554 0.0011705323 143.7992133031
## Singletons.in.Tract 0.0009412310 0.0009952295 171.9769598816
## Seniors.in.Tract 0.0005462133 0.0012941986 171.8309587391
## African.Americans.in.Tract 0.0011788070 0.0011019899 171.9265377515
## Noncitizens.in.Tract 0.0016505217 0.0008474492 151.9803456619
## High.BP 0.0000243144 0.0002100837 156.2592610355
## Binge.Drinking 0.0003568737 0.0002011089 73.2495854494
## Cancer -0.0020410923 0.0012606066 147.4497132599
## Asthma 0.0001281358 0.0006741862 76.2272780433
## Heart.Disease 0.0029349595 0.0015715446 122.9205595997
## COPD -0.0001941966 0.0012914724 119.4364440967
## Smoking -0.0002021622 0.0002613378 137.9893454612
## Diabetes -0.0008515503 0.0006359366 124.8726079012
## No.Physical.Activity 0.0000580965 0.0002404181 134.1139063008
## Obesity 0.0003620240 0.0002008568 163.2919348647
## Poor.Sleeping.Habits 0.0000868556 0.0001822556 159.8740163594
## Poor.Mental.Health -0.0000854682 0.0005510922 50.2537009475
## Testing_Rate 0.0000007758 0.0000002941 44.8632111411
## Hospitalization_Rate -0.0001228694 0.0001196445 31.8346475230
## t value Pr(>|t|)
## (Intercept) -0.949 0.3452
## Affluence 4.109 0.0000665 ***
## Singletons.in.Tract 0.946 0.3456
## Seniors.in.Tract 0.422 0.6735
## African.Americans.in.Tract 1.070 0.2863
## Noncitizens.in.Tract 1.948 0.0533 .
## High.BP 0.116 0.9080
## Binge.Drinking 1.775 0.0801 .
## Cancer -1.619 0.1076
## Asthma 0.190 0.8498
## Heart.Disease 1.868 0.0642 .
## COPD -0.150 0.8807
## Smoking -0.774 0.4405
## Diabetes -1.339 0.1830
## No.Physical.Activity 0.242 0.8094
## Obesity 1.802 0.0733 .
## Poor.Sleeping.Habits 0.477 0.6343
## Poor.Mental.Health -0.155 0.8774
## Testing_Rate 2.638 0.0114 *
## Hospitalization_Rate -1.027 0.3122
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation of fixed effects could have been required in summary()##
## Correlation of Fixed Effects:
## (Intr) Afflnc Sng..T Snr..T A.A..T Nnc..T Hgh.BP Bng.Dr Cancer
## Affluence 0.016
## Sngltns.n.T 0.020 0.069
## Snrs.n.Trct 0.474 0.345 0.189
## Afrcn.Am..T 0.123 0.148 -0.387 0.149
## Nnctzns.n.T 0.001 0.117 0.036 0.086 -0.127
## High.BP -0.075 0.260 0.019 0.073 -0.065 0.342
## Bing.Drnkng -0.392 -0.124 -0.277 -0.117 0.065 -0.018 0.129
## Cancer -0.554 -0.106 0.211 -0.251 -0.076 -0.085 -0.335 -0.051
## Asthma -0.409 -0.109 -0.265 -0.215 0.077 0.096 0.111 0.036 0.041
## Heart.Dises -0.179 0.059 -0.309 -0.175 0.250 -0.133 0.056 0.065 -0.490
## COPD 0.573 0.011 0.160 0.265 -0.045 0.244 0.071 0.028 -0.257
## Smoking -0.095 0.118 -0.177 -0.119 -0.045 0.069 -0.033 -0.278 0.080
## Diabetes 0.146 -0.378 -0.091 -0.193 -0.303 -0.234 -0.553 0.042 0.241
## N.Physcl.Ac -0.208 0.062 0.111 0.014 -0.018 -0.222 -0.013 0.117 0.443
## Obesity -0.024 0.381 0.477 0.284 0.104 0.162 -0.099 -0.188 0.114
## Pr.Slpng.Hb -0.409 -0.395 0.111 -0.326 -0.278 -0.071 -0.186 0.110 0.098
## Pr.Mntl.Hlt -0.366 0.222 -0.053 -0.028 0.072 -0.122 0.024 0.122 0.352
## Testing_Rat 0.216 -0.112 0.024 0.026 0.012 -0.015 -0.024 -0.073 -0.180
## Hsptlztn_Rt -0.111 -0.128 -0.052 -0.164 -0.052 -0.077 -0.041 -0.081 -0.074
## Asthma Hrt.Ds COPD Smokng Diabts N.Ph.A Obesty Pr.S.H Pr.M.H
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises 0.321
## COPD -0.403 -0.578
## Smoking 0.105 0.174 -0.464
## Diabetes -0.133 -0.357 0.001 0.211
## N.Physcl.Ac 0.057 -0.355 -0.005 -0.291 -0.155
## Obesity -0.212 -0.087 0.150 -0.251 -0.371 -0.004
## Pr.Slpng.Hb 0.091 0.256 -0.161 -0.082 -0.032 -0.155 -0.140
## Pr.Mntl.Hlt -0.256 0.073 -0.454 0.022 -0.006 0.002 0.021 -0.124
## Testing_Rat -0.282 -0.069 0.229 0.107 0.113 -0.276 0.092 -0.140 -0.151
## Hsptlztn_Rt 0.044 0.156 -0.104 0.060 -0.023 -0.005 0.014 0.005 -0.095
## Tstn_R
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises
## COPD
## Smoking
## Diabetes
## N.Physcl.Ac
## Obesity
## Pr.Slpng.Hb
## Pr.Mntl.Hlt
## Testing_Rat
## Hsptlztn_Rt 0.080
## fit warnings:
## Some predictor variables are on very different scales: consider rescalingthis.lme <- lmer("total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + (1 | stateID)", data = county.Demo_and_Covid.500counties)
print(summary(this.lme), correlation=TRUE)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## "total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + (1 | stateID)"
## Data: county.Demo_and_Covid.500counties
##
## REML criterion at convergence: -2430.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.8229 -0.3814 -0.0831 0.2771 6.5344
##
## Random effects:
## Groups Name Variance Std.Dev.
## stateID (Intercept) 0.000007907 0.002812
## Residual 0.000013141 0.003625
## Number of obs: 326, groups: stateID, 51
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) -0.02386140 0.00814185 192.82505213 -2.931
## Affluence 0.00303196 0.00073929 302.30000979 4.101
## Singletons.in.Tract 0.00075001 0.00069032 301.05282345 1.086
## Seniors.in.Tract 0.00024369 0.00087192 304.53300753 0.279
## African.Americans.in.Tract 0.00189729 0.00084280 306.81511704 2.251
## Noncitizens.in.Tract 0.00189289 0.00067987 271.72253115 2.784
## High.BP -0.00003031 0.00015255 298.75507418 -0.199
## Binge.Drinking 0.00040322 0.00016028 159.16744196 2.516
## Cancer -0.00029088 0.00089473 266.41391805 -0.325
## Asthma 0.00084505 0.00053125 141.53434244 1.591
## Heart.Disease 0.00317138 0.00114784 211.05409998 2.763
## COPD -0.00133304 0.00086892 205.52619856 -1.534
## Smoking -0.00020482 0.00020087 251.04702321 -1.020
## Diabetes -0.00114251 0.00043049 269.11682409 -2.654
## No.Physical.Activity 0.00031890 0.00017291 237.73388083 1.844
## Obesity 0.00025257 0.00014003 307.96857100 1.804
## Poor.Sleeping.Habits 0.00024011 0.00013482 297.27089752 1.781
## Poor.Mental.Health -0.00015941 0.00045070 103.52749015 -0.354
## Pr(>|t|)
## (Intercept) 0.00379 **
## Affluence 0.0000529 ***
## Singletons.in.Tract 0.27814
## Seniors.in.Tract 0.78006
## African.Americans.in.Tract 0.02508 *
## Noncitizens.in.Tract 0.00574 **
## High.BP 0.84265
## Binge.Drinking 0.01287 *
## Cancer 0.74536
## Asthma 0.11391
## Heart.Disease 0.00623 **
## COPD 0.12653
## Smoking 0.30887
## Diabetes 0.00843 **
## No.Physical.Activity 0.06638 .
## Obesity 0.07226 .
## Poor.Sleeping.Habits 0.07595 .
## Poor.Mental.Health 0.72429
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation of fixed effects could have been required in summary()##
## Correlation of Fixed Effects:
## (Intr) Afflnc Sng..T Snr..T A.A..T Nnc..T Hgh.BP Bng.Dr Cancer
## Affluence -0.050
## Sngltns.n.T -0.056 0.043
## Snrs.n.Trct 0.395 0.293 0.073
## Afrcn.Am..T 0.242 0.076 -0.405 0.202
## Nnctzns.n.T -0.072 0.153 0.125 0.057 -0.190
## High.BP -0.095 0.157 0.099 0.007 -0.234 0.327
## Bing.Drnkng -0.488 -0.040 -0.205 -0.068 0.042 -0.076 0.149
## Cancer -0.495 -0.095 0.231 -0.172 -0.074 -0.066 -0.329 -0.019
## Asthma -0.269 -0.096 -0.262 -0.121 -0.013 0.211 0.052 0.008 -0.157
## Heart.Dises -0.058 0.077 -0.301 -0.132 0.213 -0.054 0.000 0.034 -0.602
## COPD 0.479 0.010 0.128 0.172 -0.006 0.156 0.058 0.060 -0.212
## Smoking -0.043 0.105 -0.119 -0.137 -0.105 0.159 -0.082 -0.327 0.157
## Diabetes 0.036 -0.301 -0.078 -0.133 -0.230 -0.253 -0.446 0.075 0.367
## N.Physcl.Ac -0.116 0.034 0.101 0.079 0.059 -0.274 0.004 0.126 0.336
## Obesity -0.066 0.383 0.398 0.202 0.133 0.193 -0.103 -0.147 0.118
## Pr.Slpng.Hb -0.385 -0.351 0.162 -0.326 -0.321 -0.046 -0.156 0.087 0.028
## Pr.Mntl.Hlt -0.354 0.183 -0.008 0.022 0.051 -0.165 0.028 0.130 0.417
## Asthma Hrt.Ds COPD Smokng Diabts N.Ph.A Obesty Pr.S.H
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises 0.336
## COPD -0.322 -0.491
## Smoking 0.144 0.083 -0.476
## Diabetes -0.106 -0.432 -0.008 0.278
## N.Physcl.Ac -0.023 -0.360 0.087 -0.274 -0.169
## Obesity -0.126 -0.021 0.091 -0.220 -0.376 -0.045
## Pr.Slpng.Hb 0.000 0.239 -0.093 -0.167 -0.060 -0.153 -0.115
## Pr.Mntl.Hlt -0.437 -0.066 -0.389 -0.028 0.071 -0.086 0.025 -0.081Testing Rate
testing.data.state <- compiled.stats[[length(daily_filenames)]][, c("Province_State", "Testing_Rate")]
testing.data.state <- testing.data.state[!is.na(testing.data.state$Testing_Rate),]
testing.data.state <- testing.data.state[order(testing.data.state$Testing_Rate),]
col.state <- rep("pink", nrow(testing.data.state))
avg.test.rate <- mean(testing.data.state$Testing_Rate, na.rm = T)
col.state[testing.data.state$Testing_Rate < avg.test.rate] <- "grey"
col.state[testing.data.state$Province_State == "Oklahoma"] <- "lightblue"
par(mar = c(5,6,4,2))
barplot(testing.data.state$Testing_Rate, names.arg = testing.data.state$Province_State, horiz = T, main = "Testing Rate by State", las = 2, cex.axis = 1, cex.names = 0.5, col = col.state, border = F, xlab = "Total number of people tested per 100,000 persons.")
abline(v = avg.test.rate, col = "red")
text(x = avg.test.rate + 10, y = 1, labels = "Average Testing Rate", adj = c(0, 0.5), col = "red")
Pink highlights the last 14 days.
day.first.case <- min(which(US.total$cases.total > 100))
n.days <- nrow(US.total)
twoweek.col <- c(rep("grey", n.days-day.first.case-13), rep("pink", 14))
par(mar = c(5,5,4,2))
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$rise.cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Cases of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$rise.deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Deaths of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)